Last active
August 27, 2017 01:53
-
-
Save rsarai/6f3a24e55f03c7be4c4d2d4e752ac096 to your computer and use it in GitHub Desktop.
Spider for retrieve all the products from a web site and another one for download images and renaming them.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import scrapy | |
from scrapymercado.items import ProductsItem | |
from scrapymercado.constants import URL | |
class ProductsSpider(scrapy.Spider): | |
name = "products" | |
def start_requests(self): | |
max_page_number = 67 | |
base_url = 'http://supersecretsite.com/products' | |
yield scrapy.Request(url=base_url, callback=self.parse) | |
for idx in range(2, max_page_number + 1): | |
url = base_url + '?page=' + str(idx) | |
yield scrapy.Request(url=url, callback=self.parse) | |
def parse(self, response): | |
base_url = 'http://supersecretsite.com' | |
for product in response.css("div.product-list-item"): | |
yield { | |
'nome': product.css("span.info::text").extract_first(), | |
'preco-cheio': '3000', | |
'imagem-1': base_url + product.css("img").xpath('@src').extract()[0], | |
'categoria-nome-nivel-1': "Produtos", | |
} | |
class ProductImgSpider(scrapy.Spider): | |
name = "productsimg" | |
def start_requests(self): | |
max_page_number = 67 | |
base_url = 'http://supersecretsite.com' | |
yield scrapy.Request(url=base_url, callback=self.parse) | |
for idx in range(2, max_page_number + 1): | |
url = base_url + '?page=' + str(idx) | |
yield scrapy.Request(url=url, callback=self.parse) | |
def parse(self, response): | |
urls = URL | |
item = ProductsItem() | |
item['image_urls'] = urls | |
return item | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment